Training in progress, step 23500, checkpoint

last-checkpoint/config.json

@@ -26,7 +26,7 @@
     "rope_type": "default"
   },
   "tie_word_embeddings": false,
-  "transformers_version": "5.8.1",
+  "transformers_version": "5.9.0",
   "use_cache": false,
   "vocab_size": 50257
 }

last-checkpoint/generation_config.json

@@ -5,6 +5,6 @@
   "output_attentions": false,
   "output_hidden_states": false,
   "pad_token_id": 0,
-  "transformers_version": "5.8.1",
+  "transformers_version": "5.9.0",
   "use_cache": true
 }

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25b0a3e9e8090b5ff5092bfaa0a28abdf26af99daaf2c8b28ba8a134e93e48ca
+oid sha256:6eb1e4dd0903fe497764d955ecd2afbc2bc7c2a907a197c9b6156379fd0cb9d4
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0aabba91843ff25e6d5e79ee7c455be1a21bc0bb03ac8da99844c27b9d5ad93
+oid sha256:1d5566af4c0c91ace25af463a9fd0c35d30ac6774693e81a743459ecd8802f15
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7ae22acd598256085538c00a60824c21a89f1c7b7350117291bcd5a2a1173d2
+oid sha256:f66e48699b199955664d97c152eda4d498658e8c242bfacea1b8e34bd9e4220b
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:823e26c531197724b55bbef9899e08e04fd0839d03f4533a50acfbd40f901961
+oid sha256:9e38c3b4c9d049313a5e0f9d1718ec8e35236f2f443ecc925d89542c25ab18e0
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a93e232b49299482878a1672750e6a4fa22f4eb479d491b73d055175339a2ff
+oid sha256:dd7db22f32255632f9de493bef39e883f81b9e1f3df394e3b7c574e5214a7019
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.0017,
+  "epoch": 6.000233333333333,
   "eval_steps": 500,
-  "global_step": 23000,
+  "global_step": 23500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3228,6 +3228,76 @@
       "learning_rate": 3.988144737954481e-06,
       "loss": 0.46745311737060546,
       "step": 23000
+    },
+    {
+      "epoch": 1.0016666666666667,
+      "grad_norm": 2.0833899974823,
+      "learning_rate": 3.934067433877738e-06,
+      "loss": 0.7630504608154297,
+      "step": 23050
+    },
+    {
+      "epoch": 1.0033333333333334,
+      "grad_norm": 2.058403253555298,
+      "learning_rate": 3.880303879064737e-06,
+      "loss": 0.7528865814208985,
+      "step": 23100
+    },
+    {
+      "epoch": 1.005,
+      "grad_norm": 2.207179307937622,
+      "learning_rate": 3.826855597858376e-06,
+      "loss": 0.7208507537841797,
+      "step": 23150
+    },
+    {
+      "epoch": 1.0066666666666666,
+      "grad_norm": 2.088376998901367,
+      "learning_rate": 3.7737241056626865e-06,
+      "loss": 0.7016201019287109,
+      "step": 23200
+    },
+    {
+      "epoch": 1.0083333333333333,
+      "grad_norm": 2.3134944438934326,
+      "learning_rate": 3.720910908899886e-06,
+      "loss": 0.7238885498046875,
+      "step": 23250
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 2.1278038024902344,
+      "learning_rate": 3.6684175049676287e-06,
+      "loss": 0.6847061920166015,
+      "step": 23300
+    },
+    {
+      "epoch": 1.0116666666666667,
+      "grad_norm": 2.9893929958343506,
+      "learning_rate": 3.6162453821965983e-06,
+      "loss": 0.7510233306884766,
+      "step": 23350
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 2.13517689704895,
+      "learning_rate": 3.5643960198082636e-06,
+      "loss": 1.0430319976806641,
+      "step": 23400
+    },
+    {
+      "epoch": 1.015,
+      "grad_norm": 2.2010929584503174,
+      "learning_rate": 3.512870887872963e-06,
+      "loss": 1.0488350677490235,
+      "step": 23450
+    },
+    {
+      "epoch": 2.0004,
+      "grad_norm": 1.5543965101242065,
+      "learning_rate": 3.4616714472682326e-06,
+      "loss": 0.9235614776611328,
+      "step": 23500
     }
   ],
   "logging_steps": 50,
@@ -3247,7 +3317,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0495028719279063e+18,
+  "total_flos": 2.0965097810483773e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null