Training in progress, step 120000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37e1df7a1d5af563d39dac4475c64a25a3d966d1f87494a9c847fe983f166bd8
+oid sha256:9be11f06e3ecdd0a9b84007e37ce6faf2809282f85e55bf6ccee49748b95bc0b
 size 6961088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46b087cbcac1794815a736ae0610cb66f89b41ceefdbf2a98a7d64e4969a8e48
+oid sha256:a4ed9fe27450ad57b90172d64766e3608a42a25e5d96f770cb57796b398e19f2
 size 3583418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a15c5c1eeb4142880599a7cf455fa16fb33ff35eaae83b03134bb5e6035bca7
+oid sha256:3a3428fb9d9ea94d0008de7fc1f3f6df39de7def688d97c9d0423f69d58033bb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e81870cc69b1580d1dc882ebfa95e380308fdb3a91bad7c4f448de107a49b57a
+oid sha256:46a584dc7ef1ad2fc3c32e8d94a114415d7a967d2fe3f62cc1d8056f225970d6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9834710743801653,
+  "epoch": 0.9917355371900827,
   "eval_steps": 1000,
-  "global_step": 119000,
+  "global_step": 120000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2625,6 +2625,28 @@
       "eval_samples_per_second": 6.887,
       "eval_steps_per_second": 6.887,
       "step": 119000
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 3.4898810386657715,
+      "learning_rate": 2.4793388429752067e-07,
+      "loss": 2.9617,
+      "step": 119500
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 76.47006225585938,
+      "learning_rate": 1.6528925619834713e-07,
+      "loss": 2.8396,
+      "step": 120000
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 2.429133176803589,
+      "eval_runtime": 138.7508,
+      "eval_samples_per_second": 6.933,
+      "eval_steps_per_second": 6.933,
+      "step": 120000
     }
   ],
   "logging_steps": 500,
@@ -2632,7 +2654,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 1000,
-  "total_flos": 3.026405427716183e+18,
+  "total_flos": 3.0518878821174374e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null