Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:093c15f2fded96bff0e61da05e2c51d06d69f0e739da21a1fd32ba1c4321340c
+oid sha256:04added5791a29bc84cdcc28e97f7d0da93b1c4401ce9866aa7a7ad46307a7c0
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc3d5df975d3fbc07815abcc1e685622664fd8b7499af7e6ab1d766e5435b843
+oid sha256:5884c1b5cebd9f96ee84a113c8720c645ffba48617676abf0beab6bb6a274eb0
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
+oid sha256:b90a19943f8ef28f7f3c1abafd8de7b24ff68c3eda11dffdc748b1a1d989fcb2
 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": 0.028037383177570093,
+  "epoch": 0.04205607476635514,
   "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": 31.446,
       "eval_steps_per_second": 15.896,
       "step": 6
+    },
+    {
+      "epoch": 0.03271028037383177,
+      "grad_norm": 1.7515218257904053,
+      "learning_rate": 0.00014,
+      "loss": 2.1706,
+      "step": 7
+    },
+    {
+      "epoch": 0.037383177570093455,
+      "grad_norm": 1.8548814058303833,
+      "learning_rate": 0.00016,
+      "loss": 2.0207,
+      "step": 8
+    },
+    {
+      "epoch": 0.04205607476635514,
+      "grad_norm": 1.8166495561599731,
+      "learning_rate": 0.00018,
+      "loss": 1.6433,
+      "step": 9
+    },
+    {
+      "epoch": 0.04205607476635514,
+      "eval_loss": 1.5704231262207031,
+      "eval_runtime": 2.8923,
+      "eval_samples_per_second": 31.463,
+      "eval_steps_per_second": 15.904,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1109738548887552.0,
+  "total_flos": 1664607823331328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null