Training in progress, step 140, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:712500642cd5eacaf2d3d13424057784a9a6b504e88ecf383e62482119ab96b6
+oid sha256:ff33b28108b3679d7be04706c6f792227844ae4246a7458e95f560f317bb2d0d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc54186d6a7952617779177df5659ed1e0adab55bf50305de35608da22734c49
+oid sha256:cef79a8dc424dcfafd9e0823028c49d788f31347b10bfd56f7b6b4e6bc1f8070
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79354fda314c9103e2d55f6fd0e3e7ec5fe801812e33d2c8e4dd8c180772e09a
+oid sha256:ad528149b7ddaf36aa54c3270bc91600bfb527af6fb344cfc62207a9548bc407
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fc750a6dfb3e5c9f642238b7443b0984a56e79b7c2731a6e152ecfc3e32f4e7
+oid sha256:671828e69cd8fd42106344a5797cbc78f701a434a6386d9dfacd16451ba179aa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06601870529983496,
+  "epoch": 0.06846384253316218,
   "eval_steps": 34,
-  "global_step": 135,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -984,6 +984,49 @@
       "learning_rate": 6.387583338128471e-05,
       "loss": 1.074,
       "step": 135
+    },
+    {
+      "epoch": 0.0665077327465004,
+      "grad_norm": 1.2866921424865723,
+      "learning_rate": 6.215889499576898e-05,
+      "loss": 1.1369,
+      "step": 136
+    },
+    {
+      "epoch": 0.0665077327465004,
+      "eval_loss": 1.008103847503662,
+      "eval_runtime": 1314.805,
+      "eval_samples_per_second": 1.965,
+      "eval_steps_per_second": 0.655,
+      "step": 136
+    },
+    {
+      "epoch": 0.06699676019316585,
+      "grad_norm": 1.012360692024231,
+      "learning_rate": 6.0454879312945754e-05,
+      "loss": 0.923,
+      "step": 137
+    },
+    {
+      "epoch": 0.06748578763983129,
+      "grad_norm": 1.1338571310043335,
+      "learning_rate": 5.876436825260967e-05,
+      "loss": 0.8111,
+      "step": 138
+    },
+    {
+      "epoch": 0.06797481508649673,
+      "grad_norm": 1.3135179281234741,
+      "learning_rate": 5.708793912273911e-05,
+      "loss": 1.0341,
+      "step": 139
+    },
+    {
+      "epoch": 0.06846384253316218,
+      "grad_norm": 1.311312198638916,
+      "learning_rate": 5.542616442234618e-05,
+      "loss": 1.0275,
+      "step": 140
     }
   ],
   "logging_steps": 1,
@@ -1003,7 +1046,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.992588163992781e+17,
+  "total_flos": 6.214535873770291e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null