Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

checkpoint-1000/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "RajuKandasamy/tamillama_tiny_30m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 786,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32001
+}

checkpoint-1000/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "pad_token_id": 1,
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": false
+}

checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e67f5009a250f2d9c94dfc23f696043361e95e40ee9e8c3d12eef5be073b86a0
+size 120998648

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b37cdd41b861b1a00bb4fa687e537fdc5092a8cdb2f37cf1ca136cc9c1fd1eb
+size 242089082

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea005b38dffb3ddb68fe35f651e4ee5e119bf913293dda58efdd7f56f4335656
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:773c1ef53a65c444ad5d96a455011e0c8e03be3c3c98750c5a494ea1c70c2a28
+size 1064

checkpoint-1000/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.49975012493753124,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24987506246876562,
+      "grad_norm": 1.422733187675476,
+      "learning_rate": 4.5835415625520576e-05,
+      "loss": 6.5696,
+      "step": 500
+    },
+    {
+      "epoch": 0.49975012493753124,
+      "grad_norm": 1.82273268699646,
+      "learning_rate": 4.167083125104115e-05,
+      "loss": 4.7727,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6003,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 135495942144000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb6f30cb8beaebf42035cec064257dc73ecd20aac591d533807023b0cc182733
+size 5240

checkpoint-1500/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "RajuKandasamy/tamillama_tiny_30m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 786,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32001
+}

checkpoint-1500/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "pad_token_id": 1,
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": false
+}

checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6945aff376efd11d24c745a2179caf8fcf994122011ac4aca3461717aa4fda48
+size 120998648

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88acfb54df5799d88cf7bcfdecb1f741088b16c354abf1d366ab870c409941f7
+size 242089082

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea005b38dffb3ddb68fe35f651e4ee5e119bf913293dda58efdd7f56f4335656
+size 14244

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85746fcb95f2620697689a2f0a77790355e75fa81fea04251c19c0bb3ad811fa
+size 1064

checkpoint-1500/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7496251874062968,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24987506246876562,
+      "grad_norm": 1.422733187675476,
+      "learning_rate": 4.5835415625520576e-05,
+      "loss": 6.5696,
+      "step": 500
+    },
+    {
+      "epoch": 0.49975012493753124,
+      "grad_norm": 1.82273268699646,
+      "learning_rate": 4.167083125104115e-05,
+      "loss": 4.7727,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7496251874062968,
+      "grad_norm": 2.662141799926758,
+      "learning_rate": 3.7506246876561725e-05,
+      "loss": 4.4216,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6003,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 203243913216000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb6f30cb8beaebf42035cec064257dc73ecd20aac591d533807023b0cc182733
+size 5240

checkpoint-2000/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "RajuKandasamy/tamillama_tiny_30m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 786,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32001
+}

checkpoint-2000/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "pad_token_id": 1,
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": false
+}

checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87dd617d10fbb597da567fc1fa2cb005aab33015645be8b0b8fd41c93580f68a
+size 120998648

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cef7d6274639c009e8504bb5630231ef7d05aa6a86f5fe947500dff6f593a682
+size 242089082

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea005b38dffb3ddb68fe35f651e4ee5e119bf913293dda58efdd7f56f4335656
+size 14244

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89c5dd2ba40335251651e1bf6d6f55a6231bcff52aafbb100d6cf7d5961d5d89
+size 1064

checkpoint-2000/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9995002498750625,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24987506246876562,
+      "grad_norm": 1.422733187675476,
+      "learning_rate": 4.5835415625520576e-05,
+      "loss": 6.5696,
+      "step": 500
+    },
+    {
+      "epoch": 0.49975012493753124,
+      "grad_norm": 1.82273268699646,
+      "learning_rate": 4.167083125104115e-05,
+      "loss": 4.7727,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7496251874062968,
+      "grad_norm": 2.662141799926758,
+      "learning_rate": 3.7506246876561725e-05,
+      "loss": 4.4216,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9995002498750625,
+      "grad_norm": 2.524129629135132,
+      "learning_rate": 3.334166250208229e-05,
+      "loss": 4.178,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6003,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 270991884288000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb6f30cb8beaebf42035cec064257dc73ecd20aac591d533807023b0cc182733
+size 5240

checkpoint-2500/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "RajuKandasamy/tamillama_tiny_30m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 786,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32001
+}

checkpoint-2500/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "pad_token_id": 1,
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": false
+}

checkpoint-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc79216580f30ec62c5f1251131b92a510f1147518ec4253f5097c91dd3ae305
+size 120998648

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4a98acc9b8815d9ce3ca376f17194c94f3e6820cb04e7d26996e1b8b4ced7d1
+size 242089082

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c44141bbdc09951afac7e1120c543329e05011264f0246580d2c7b808a155c7
+size 14244

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b0e74352a7a9430e4ccea6937b4aac21c15810086a614b63b55cdc40a702df8
+size 1064

checkpoint-2500/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.249375312343828,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24987506246876562,
+      "grad_norm": 1.422733187675476,
+      "learning_rate": 4.5835415625520576e-05,
+      "loss": 6.5696,
+      "step": 500
+    },
+    {
+      "epoch": 0.49975012493753124,
+      "grad_norm": 1.82273268699646,
+      "learning_rate": 4.167083125104115e-05,
+      "loss": 4.7727,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7496251874062968,
+      "grad_norm": 2.662141799926758,
+      "learning_rate": 3.7506246876561725e-05,
+      "loss": 4.4216,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9995002498750625,
+      "grad_norm": 2.524129629135132,
+      "learning_rate": 3.334166250208229e-05,
+      "loss": 4.178,
+      "step": 2000
+    },
+    {
+      "epoch": 1.249375312343828,
+      "grad_norm": 2.6071786880493164,
+      "learning_rate": 2.917707812760287e-05,
+      "loss": 3.9573,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6003,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 338705981374464.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb6f30cb8beaebf42035cec064257dc73ecd20aac591d533807023b0cc182733
+size 5240

checkpoint-3000/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "RajuKandasamy/tamillama_tiny_30m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 786,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32001
+}

checkpoint-3000/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "pad_token_id": 1,
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": false
+}

checkpoint-3000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc92bfc7ab464809fae8ad5b692e357003356a2b0c91f3ff49b53aac6642ef6
+size 120998648

checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fd09eb388839f5c041e1e84511022068a25c95d3d6692719fd3d339b58831ad
+size 242089082

checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c44141bbdc09951afac7e1120c543329e05011264f0246580d2c7b808a155c7
+size 14244

checkpoint-3000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e742b5da5a6a29be39d53f608c57d8a76037d5dbd851f02daab87e72860ba04d
+size 1064

checkpoint-3000/trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4992503748125938,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24987506246876562,
+      "grad_norm": 1.422733187675476,
+      "learning_rate": 4.5835415625520576e-05,
+      "loss": 6.5696,
+      "step": 500
+    },
+    {
+      "epoch": 0.49975012493753124,
+      "grad_norm": 1.82273268699646,
+      "learning_rate": 4.167083125104115e-05,
+      "loss": 4.7727,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7496251874062968,
+      "grad_norm": 2.662141799926758,
+      "learning_rate": 3.7506246876561725e-05,
+      "loss": 4.4216,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9995002498750625,
+      "grad_norm": 2.524129629135132,
+      "learning_rate": 3.334166250208229e-05,
+      "loss": 4.178,
+      "step": 2000
+    },
+    {
+      "epoch": 1.249375312343828,
+      "grad_norm": 2.6071786880493164,
+      "learning_rate": 2.917707812760287e-05,
+      "loss": 3.9573,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4992503748125938,
+      "grad_norm": 2.997709274291992,
+      "learning_rate": 2.501249375312344e-05,
+      "loss": 3.86,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6003,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 406453952446464.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb6f30cb8beaebf42035cec064257dc73ecd20aac591d533807023b0cc182733
+size 5240

checkpoint-3500/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "RajuKandasamy/tamillama_tiny_30m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 786,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32001
+}

checkpoint-3500/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "pad_token_id": 1,
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": false
+}

checkpoint-3500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b7df3af6edc0577c303aa3e79aeb5a9a870b43d0fafee0423a1f03d4763029
+size 120998648

checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af1ceed33965ab3cd717b9b8758e04c5b1b559482a8a1b94d2195c245136581e
+size 242089082

checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c44141bbdc09951afac7e1120c543329e05011264f0246580d2c7b808a155c7
+size 14244

checkpoint-3500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d98a12675e85ec1c1e84206a6eee6abc4af6262538de4752065ab3f52b793c21
+size 1064

checkpoint-3500/trainer_state.json

@@ -0,0 +1,82 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.7491254372813594,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24987506246876562,
+      "grad_norm": 1.422733187675476,
+      "learning_rate": 4.5835415625520576e-05,
+      "loss": 6.5696,
+      "step": 500
+    },
+    {
+      "epoch": 0.49975012493753124,
+      "grad_norm": 1.82273268699646,
+      "learning_rate": 4.167083125104115e-05,
+      "loss": 4.7727,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7496251874062968,
+      "grad_norm": 2.662141799926758,
+      "learning_rate": 3.7506246876561725e-05,
+      "loss": 4.4216,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9995002498750625,
+      "grad_norm": 2.524129629135132,
+      "learning_rate": 3.334166250208229e-05,
+      "loss": 4.178,
+      "step": 2000
+    },
+    {
+      "epoch": 1.249375312343828,
+      "grad_norm": 2.6071786880493164,
+      "learning_rate": 2.917707812760287e-05,
+      "loss": 3.9573,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4992503748125938,
+      "grad_norm": 2.997709274291992,
+      "learning_rate": 2.501249375312344e-05,
+      "loss": 3.86,
+      "step": 3000
+    },
+    {
+      "epoch": 1.7491254372813594,
+      "grad_norm": 2.626232862472534,
+      "learning_rate": 2.084790937864401e-05,
+      "loss": 3.7562,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6003,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 474201923518464.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb6f30cb8beaebf42035cec064257dc73ecd20aac591d533807023b0cc182733
+size 5240

checkpoint-4000/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "RajuKandasamy/tamillama_tiny_30m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 786,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32001
+}