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:b13ed147644620729c239157741e06e052419dd5b42b3b75425e7037bed5fef8
+oid sha256:caa5d1ec62ea53d864bf7484aaaa2a772c1d5b8119b31c17b42d617e38783082
 size 604317736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2c90e728e473ac8b80e35f25c41a90d578a157fe0b83850f190acc190a5d8c7
+oid sha256:28d2df625b68a4fb865cf5394787a6ea912536849f1212162e3be322e06cecce
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09acce823b858db1a079a05549bd8528f2fec468928dba778f7e8bdddcd10eea
+oid sha256:332d05b227720963e561614b208f5e39d94130cc5b67b712d8aec704897dc6e6
 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": 7.759557187936475e-05,
+  "epoch": 0.00011639335781904713,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,35 @@
       "eval_samples_per_second": 17.42,
       "eval_steps_per_second": 8.71,
       "step": 6
+    },
+    {
+      "epoch": 9.052816719259221e-05,
+      "grad_norm": 1.0958664417266846,
+      "learning_rate": 0.00014,
+      "loss": 0.7754,
+      "step": 7
+    },
+    {
+      "epoch": 0.00010346076250581966,
+      "grad_norm": 1.603328824043274,
+      "learning_rate": 0.00016,
+      "loss": 0.8923,
+      "step": 8
+    },
+    {
+      "epoch": 0.00011639335781904713,
+      "grad_norm": 1.5763895511627197,
+      "learning_rate": 0.00018,
+      "loss": 0.8057,
+      "step": 9
+    },
+    {
+      "epoch": 0.00011639335781904713,
+      "eval_loss": 0.48591652512550354,
+      "eval_runtime": 1827.9834,
+      "eval_samples_per_second": 17.811,
+      "eval_steps_per_second": 8.905,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -84,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 977240485527552.0,
+  "total_flos": 1465860728291328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null