Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:888d6b2d183be0ad051b69e15bacc2f610a2138674c1cefb759c0b5ea44fb84b
+oid sha256:e737501f2b45e7567ee47af1ddb09b9cbaa6f653e680bb4a4cad7d8ad854e388
 size 4725640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3da76e9afdf003a898a487820cd7ea1d43e840d64f8865874b93117bab741801
+oid sha256:b322f65dbb3d497733de58208d7e2ff958939a0bbcd4b0f1665fb36b3e6d1a6f
 size 2423738

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28d42be630248a5213a70ba5e163d2391a05816dbb273d1b7b48dcd47e871fb4
+oid sha256:3d1dbd056bdba902bbd15884fe0ae45df7b81d1dab50b96a0c9b32d0eae3e262
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da2b3df137afc8ce0bf3abe9574aa4eb50b6c5bd11e6952c66c439eade1cc134
+oid sha256:35b984f5d5bfe5a9a68144cbebc8463a6390d9811bce29b59e9d59016179fb2e
 size 1064

last-checkpoint/tokenizer_config.json

@@ -37,12 +37,9 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "max_length": 2048,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",
-  "padding": true,
   "padding_side": "right",
   "tokenizer_class": "BloomTokenizer",
-  "truncation": true,
   "unk_token": "<unk>"
 }

last-checkpoint/trainer_state.json

@@ -1,41 +1,27 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.669515070859891e-05,
+  "epoch": 0.002725538293813028,
   "eval_steps": 500,
-  "global_step": 60,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0,
-      "grad_norm": 4.044270038604736,
-      "learning_rate": 1.6666666666666667e-06,
-      "loss": 3.7393,
+      "grad_norm": 0.39290162920951843,
+      "learning_rate": 1.5833333333333336e-06,
+      "loss": 4.0074,
       "step": 20
-    },
-    {
-      "epoch": 0.0,
-      "grad_norm": 1.908144235610962,
-      "learning_rate": 3.2500000000000002e-06,
-      "loss": 3.6056,
-      "step": 40
-    },
-    {
-      "epoch": 0.0,
-      "grad_norm": 1.030365228652954,
-      "learning_rate": 4.9166666666666665e-06,
-      "loss": 3.526,
-      "step": 60
     }
   ],
   "logging_steps": 20,
   "max_steps": 20000,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 3,
   "save_steps": 20,
-  "total_flos": 35326762795008.0,
+  "total_flos": 9824796131328.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67d9137f50a05785e0ffd11f3ee590825d65f6fa4ba75fb2184bf1dc9266179b
+oid sha256:5e76cb4f6a41bce2aadf48ff7cb6d05ab2c9b686a1100b4a6b9867db37ed9160
 size 4984