Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e36740ee494ac54caf06e7fd05ef351a11ed88492d53fdf19688921e9678a26b
+oid sha256:2fd61cb4019b150dada128125ec822c5b72137e8c272c68216be4046095f9bc9
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b59c23068d4df3753cc74f8a347c5a4cd0260d3d8b84f61649355b1d1a1485c1
+oid sha256:b412be41733f0ebe23c8ad8793df6f7a5b9890c4f38e716c108dd96aaed1234e
 size 25859156

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d6bd60281b305485221edf25562b2ccf279558c0ad3bc6188c472d7a6c91b4c
+oid sha256:e4337f3fec9046d4a616ecff2e93493e9795821eb9efddbe5a5f6bd96bc45173
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93276b798fb2abdf2e68a63204630a20a83a12a517e968355979b9b85b457e3b
+oid sha256:f289d0df8ec8a6536b87c21a77c55e71d92cbb6166908d91730d04eca8586dbc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b85362b5c3b8aa8b1d497c1686af1d1912c8e0dbdf59704e753d14829f93ee5f
+oid sha256:943ffa179ca6b61867cc4015d4e97fff8c1eeaecf49793447b4cabca8689aa13
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acbf90b44f1e9085f310209cd01b0324482a4f0bf51e1623dff812b0f43c42e9
+oid sha256:c735c7d6f164a6fba520861ecf52b6d717d49df96dcf80d2e412f455b551be24
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18874773139745918,
+  "epoch": 0.2831215970961887,
   "eval_steps": 10,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -66,6 +66,28 @@
       "learning_rate": 6.91341716182545e-05,
       "loss": 4.3577,
       "step": 25
+    },
+    {
+      "epoch": 0.2177858439201452,
+      "grad_norm": 4.010653495788574,
+      "learning_rate": 5e-05,
+      "loss": 4.3569,
+      "step": 30
+    },
+    {
+      "epoch": 0.2177858439201452,
+      "eval_loss": 0.9906569123268127,
+      "eval_runtime": 2.2155,
+      "eval_samples_per_second": 104.718,
+      "eval_steps_per_second": 13.09,
+      "step": 30
+    },
+    {
+      "epoch": 0.2540834845735027,
+      "grad_norm": 3.135490894317627,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 4.309,
+      "step": 35
     }
   ],
   "logging_steps": 5,
@@ -85,7 +107,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9936845429276672.0,
+  "total_flos": 1.4939691518263296e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null