Upload with huggingface_hub

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "JackFram/llama-160m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.28.0.dev0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78061341248b59a753aa4985e6afe1d59c37b3b2d1deec2bbc20b64fd91c8037
+size 1299404037

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c94d532697d502e30ca23b3168631ec80574e617e710c4171b2a8d68ca72cb56
+size 649710859

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8bd695bd472710b74beff7ecf0f66d54c9600ea1116f2be15428d227ee3aa0c
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0ba46f8cf4335cacf6fdf3a85777b803172634e815cf4b606ae6c2c7c50ef9c
+size 623

trainer_state.json

@@ -0,0 +1,184 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.991695501730105,
+  "global_step": 4332,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00027499999999999996,
+      "loss": 2.3243,
+      "step": 361
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.3360440731048584,
+      "eval_runtime": 81.7171,
+      "eval_samples_per_second": 457.077,
+      "eval_steps_per_second": 57.136,
+      "step": 361
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00025,
+      "loss": 1.9943,
+      "step": 722
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.3849265575408936,
+      "eval_runtime": 80.8133,
+      "eval_samples_per_second": 462.189,
+      "eval_steps_per_second": 57.775,
+      "step": 722
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.000225,
+      "loss": 1.7331,
+      "step": 1083
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.5010716915130615,
+      "eval_runtime": 80.8638,
+      "eval_samples_per_second": 461.9,
+      "eval_steps_per_second": 57.739,
+      "step": 1083
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00019993074792243765,
+      "loss": 1.463,
+      "step": 1445
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.7065136432647705,
+      "eval_runtime": 80.5929,
+      "eval_samples_per_second": 463.453,
+      "eval_steps_per_second": 57.933,
+      "step": 1445
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.00017493074792243764,
+      "loss": 1.1969,
+      "step": 1806
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.9511666297912598,
+      "eval_runtime": 80.4169,
+      "eval_samples_per_second": 464.467,
+      "eval_steps_per_second": 58.06,
+      "step": 1806
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.00014993074792243766,
+      "loss": 0.9339,
+      "step": 2167
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 3.2412941455841064,
+      "eval_runtime": 80.5491,
+      "eval_samples_per_second": 463.705,
+      "eval_steps_per_second": 57.965,
+      "step": 2167
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.00012493074792243767,
+      "loss": 0.6915,
+      "step": 2528
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 3.56394362449646,
+      "eval_runtime": 79.8139,
+      "eval_samples_per_second": 467.976,
+      "eval_steps_per_second": 58.499,
+      "step": 2528
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 9.986149584487533e-05,
+      "loss": 0.4811,
+      "step": 2890
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 3.897730827331543,
+      "eval_runtime": 80.0943,
+      "eval_samples_per_second": 466.338,
+      "eval_steps_per_second": 58.294,
+      "step": 2890
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 7.486149584487535e-05,
+      "loss": 0.3195,
+      "step": 3251
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 4.2111005783081055,
+      "eval_runtime": 79.9229,
+      "eval_samples_per_second": 467.338,
+      "eval_steps_per_second": 58.419,
+      "step": 3251
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4.986149584487534e-05,
+      "loss": 0.211,
+      "step": 3612
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 4.46787166595459,
+      "eval_runtime": 80.4105,
+      "eval_samples_per_second": 464.504,
+      "eval_steps_per_second": 58.065,
+      "step": 3612
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 2.4861495844875343e-05,
+      "loss": 0.1515,
+      "step": 3973
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 4.6477370262146,
+      "eval_runtime": 80.1153,
+      "eval_samples_per_second": 466.216,
+      "eval_steps_per_second": 58.279,
+      "step": 3973
+    },
+    {
+      "epoch": 11.99,
+      "learning_rate": 0.0,
+      "loss": 0.1233,
+      "step": 4332
+    },
+    {
+      "epoch": 11.99,
+      "eval_loss": 4.7357659339904785,
+      "eval_runtime": 80.0925,
+      "eval_samples_per_second": 466.348,
+      "eval_steps_per_second": 58.295,
+      "step": 4332
+    }
+  ],
+  "max_steps": 4332,
+  "num_train_epochs": 12,
+  "total_flos": 1.705389820458624e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d9920ef5e4c1541d141de40e5b4a77b8ad3a3f0542394222f5a8a9f674db15d
+size 3567