Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31039ae079f09a1b104f48cbb66f2666b9c1a1fb741081774af357a45d793dbc
+oid sha256:fdb466d41cdbdd782720acdb49ec20513f9650e82fc3bb3bd76f392060cde12b
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd24ff47432c8a9e0927320aadeea3545af04dc2ef4ea80d33d0a3f0d34249e1
+oid sha256:65a9b0c5883e3b804a88bb07e95dc3c6e7a7f3def193fa439fab29679bcadaf0
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7bad38b6510dcfd435e5e047c00ab3bb954cd2dc192cb4716bc78ccd281cb39
+oid sha256:4f428c8a6a024f6338900342bc9c5ff40c342f28b297a96dfc6c96a2bb31282f
 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": 0.0009812740207703,
+  "epoch": 0.0014719110311554502,
   "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": 46.56,
       "eval_steps_per_second": 23.289,
       "step": 6
+    },
+    {
+      "epoch": 0.0011448196908986834,
+      "grad_norm": 11.994471549987793,
+      "learning_rate": 0.00014,
+      "loss": 19.3337,
+      "step": 7
+    },
+    {
+      "epoch": 0.0013083653610270669,
+      "grad_norm": 12.117486953735352,
+      "learning_rate": 0.00016,
+      "loss": 20.1793,
+      "step": 8
+    },
+    {
+      "epoch": 0.0014719110311554502,
+      "grad_norm": 15.454221725463867,
+      "learning_rate": 0.00018,
+      "loss": 17.9427,
+      "step": 9
+    },
+    {
+      "epoch": 0.0014719110311554502,
+      "eval_loss": 4.7068657875061035,
+      "eval_runtime": 55.2825,
+      "eval_samples_per_second": 46.579,
+      "eval_steps_per_second": 23.299,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 391769594265600.0,
+  "total_flos": 587654391398400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null