Training in progress, step 121000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b157821f72f6473178edbe571a16c8db2d64bb4767693877fbcf40fa7c3e0a22
+oid sha256:a3180dde5b242a076dbaa1a3d3a4b22e8c70d6da569138f24e8f9b0fd942392b
 size 6303624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4876331b41affbd88dd42778652c058a3f3e72b68372b63371df38321fd25231
+oid sha256:97c46effc410c03e01a40df1b6bbf38cd8d4eb3fd0b53344d68caf8ce6c3945c
 size 3241914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c94bf8032abf4e2e9980c7ff88b65d5e34e262d076022a184a9eb558df6031a
+oid sha256:c98425f4d883fbbe5134a5df2031a37e38d93d5f48532622c72d179361669480
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46a584dc7ef1ad2fc3c32e8d94a114415d7a967d2fe3f62cc1d8056f225970d6
+oid sha256:a0c3c90e2c1736a33d5818cc3e448d6cb5702b7e18a60c866d95a0bf08bed2fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9917355371900827,
+  "epoch": 1.0,
   "eval_steps": 1000,
-  "global_step": 120000,
+  "global_step": 121000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2647,6 +2647,28 @@
       "eval_samples_per_second": 7.437,
       "eval_steps_per_second": 7.437,
       "step": 120000
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 127.4374008178711,
+      "learning_rate": 8.264462809917357e-08,
+      "loss": 2.2444,
+      "step": 120500
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 16.71834945678711,
+      "learning_rate": 0.0,
+      "loss": 2.0582,
+      "step": 121000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.690514326095581,
+      "eval_runtime": 129.3588,
+      "eval_samples_per_second": 7.437,
+      "eval_steps_per_second": 7.437,
+      "step": 121000
     }
   ],
   "logging_steps": 500,
@@ -2654,7 +2676,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 1000,
-  "total_flos": 3.045814487779564e+18,
+  "total_flos": 3.0709961419882885e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null