Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ab45e2eaf0b81a5215885dcd3644b269ef2b8e5ee97070cd6714f4cf1ff5c5d
+oid sha256:fe3c1b8675f786e39f2b36c1787e73a43ebb17a4ff86192e46c8c062e52e9b4e
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4a038450e9c80f5679886e2de9773950f7cb1a017c7ad70e3cc0bdef563d7b
+oid sha256:2671c9929da363d3c9f694da2aa91986701f3ca7d21390563e77f49b3c5047cd
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52de5368f5ce61262c2d589ee36ea6650cbb194994badad3cc71c4ee2f14c31
+oid sha256:9a0d178020fecc5513a454227b25f3a8a60c61c1b470c9504f50321e953b23a6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
+oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0198000198000198,
+  "epoch": 0.0297000297000297,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 11.945,
       "eval_steps_per_second": 5.975,
       "step": 100
+    },
+    {
+      "epoch": 0.02178002178002178,
+      "grad_norm": 0.9973340630531311,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 3.1706,
+      "step": 110
+    },
+    {
+      "epoch": 0.02376002376002376,
+      "grad_norm": 1.116804838180542,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 3.1213,
+      "step": 120
+    },
+    {
+      "epoch": 0.02574002574002574,
+      "grad_norm": 2.213376760482788,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 3.794,
+      "step": 130
+    },
+    {
+      "epoch": 0.02772002772002772,
+      "grad_norm": 1.6930793523788452,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 3.3669,
+      "step": 140
+    },
+    {
+      "epoch": 0.0297000297000297,
+      "grad_norm": 1.3636667728424072,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 3.2829,
+      "step": 150
+    },
+    {
+      "epoch": 0.0297000297000297,
+      "eval_loss": 0.8442820310592651,
+      "eval_runtime": 178.1045,
+      "eval_samples_per_second": 11.942,
+      "eval_steps_per_second": 5.974,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.883900991012864e+16,
+  "total_flos": 7.3218937061376e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null