Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2963c2a4f2a7eaa61f07ba73a60b329e7c773fb31384455fc331945f47e37cd
+oid sha256:db512f1b45379144d6d80eeae2c5d36ebe3194838652e3d66da47c1ec1912ea0
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18f04fd04382aa5d4dafd98fd6464a92640abcf8c83cb319f966fc0cc49f52ad
+oid sha256:c4c9deaad46766ff8e4caabdcb4fd357606a69a76210fb23feb9eaab1da305e9
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f03fbef729f64ddf68b55e06f01e7bb1d8bf0494ed9ac87477f34ab984a1d9b
+oid sha256:a6ab9b9869e601adf44834e3a12d4a18fbed8343468019356d2f3491dc62e15c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
+oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03936039360393604,
+  "epoch": 0.04428044280442804,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 7.288,
       "eval_steps_per_second": 0.913,
       "step": 72
+    },
+    {
+      "epoch": 0.04100041000410004,
+      "grad_norm": 0.1970762312412262,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.5685,
+      "step": 75
+    },
+    {
+      "epoch": 0.04264042640426404,
+      "grad_norm": 0.19608396291732788,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.6088,
+      "step": 78
+    },
+    {
+      "epoch": 0.04428044280442804,
+      "grad_norm": 0.17808747291564941,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.5845,
+      "step": 81
+    },
+    {
+      "epoch": 0.04428044280442804,
+      "eval_loss": 0.6018369197845459,
+      "eval_runtime": 422.6566,
+      "eval_samples_per_second": 7.29,
+      "eval_steps_per_second": 0.913,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8808127625363456e+17,
+  "total_flos": 2.1188066446147584e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null