Training in progress, step 121000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9be11f06e3ecdd0a9b84007e37ce6faf2809282f85e55bf6ccee49748b95bc0b
+oid sha256:ec74feb947721b5d200579a92d514991184a83df2d1ed9e81327d38f3a5e772c
 size 6961088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4ed9fe27450ad57b90172d64766e3608a42a25e5d96f770cb57796b398e19f2
+oid sha256:59810f65fa58cdaabc1ff0d01f55e57509d142e8e8740f9a19f7777d871ac728
 size 3583418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a3428fb9d9ea94d0008de7fc1f3f6df39de7def688d97c9d0423f69d58033bb
+oid sha256:fcbb0417ae3e9404097be4229e25590a2d724c3b6312bffabad5c5aad04d09e2
 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": 6.933,
       "eval_steps_per_second": 6.933,
       "step": 120000
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 143.42933654785156,
+      "learning_rate": 8.264462809917357e-08,
+      "loss": 2.9364,
+      "step": 120500
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 37.042301177978516,
+      "learning_rate": 0.0,
+      "loss": 2.6683,
+      "step": 121000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.4457602500915527,
+      "eval_runtime": 136.676,
+      "eval_samples_per_second": 7.039,
+      "eval_steps_per_second": 7.039,
+      "step": 121000
     }
   ],
   "logging_steps": 500,
@@ -2654,7 +2676,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 1000,
-  "total_flos": 3.0518878821174374e+18,
+  "total_flos": 3.0771197488774195e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null