Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:531827cbbf4e74337732f326db7e3e5cd013c01c3cb6ebb78b6681fc44ff3cf3
+oid sha256:7f677c97b1c72da84f99488cf53cb9fdab83e077a61c46374c715cddcc026735
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b44234bbb3ea22d0d0c5395e6e1ba4992afa9ec1d2c547b9828cc83089e3cf7
+oid sha256:85d79062ac062ec0f217e6312d0442eb7e26913bb7a9c1ea27467cc55954c07c
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d096002160b6f6344e44b161020fd5f8176aab00ff00fe8c5ea42cb9ad318a93
+oid sha256:0ebb3a935f103fde8d7d593f6c636206ae47877a48e671f781108f4a0a6cbb96
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0058809115412889,
+  "epoch": 0.008821367311933349,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 122.104,
       "eval_steps_per_second": 61.052,
       "step": 6
+    },
+    {
+      "epoch": 0.00686106346483705,
+      "grad_norm": 0.6363251209259033,
+      "learning_rate": 0.00014,
+      "loss": 2.2288,
+      "step": 7
+    },
+    {
+      "epoch": 0.0078412153883852,
+      "grad_norm": 0.6005361080169678,
+      "learning_rate": 0.00016,
+      "loss": 2.3312,
+      "step": 8
+    },
+    {
+      "epoch": 0.008821367311933349,
+      "grad_norm": 0.6487131118774414,
+      "learning_rate": 0.00018,
+      "loss": 2.4898,
+      "step": 9
+    },
+    {
+      "epoch": 0.008821367311933349,
+      "eval_loss": 2.3651981353759766,
+      "eval_runtime": 3.5733,
+      "eval_samples_per_second": 120.336,
+      "eval_steps_per_second": 60.168,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 20575590285312.0,
+  "total_flos": 30863385427968.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null