Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac40423be32af77d424f753fe71966100996c1f80afcba6f203363d063a69ae8
+oid sha256:d03773c7b6541e8c51cb10f2d051c5ebf1e812257a10272c95cd3fb1eeb47754
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47d69998977eccd1a9803d4227d0aae121567f31b3ef8a6216fb9f2ae5a73e21
+oid sha256:efad2a39037cd9799d08c92e67e686d12011ab80209a1e596a4e647d808d23b8
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbf05769fc7548beeabe0a30e68eb04a7c42955f543295d692f4a134e071bb9d
+oid sha256:cbf3498852987faa194eac66ece0f7e5985a7523269b253e1758c37d20246ad3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0003947030846046062,
+  "epoch": 0.0007894061692092124,
   "eval_steps": 3,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0001,
       "loss": 3.0494,
       "step": 5
+    },
+    {
+      "epoch": 0.00047364370152552744,
+      "grad_norm": 2.5712947845458984,
+      "learning_rate": 0.00012,
+      "loss": 1.9739,
+      "step": 6
+    },
+    {
+      "epoch": 0.00047364370152552744,
+      "eval_loss": 2.181999921798706,
+      "eval_runtime": 1036.9224,
+      "eval_samples_per_second": 5.144,
+      "eval_steps_per_second": 2.572,
+      "step": 6
+    },
+    {
+      "epoch": 0.0005525843184464486,
+      "grad_norm": 2.8870301246643066,
+      "learning_rate": 0.00014,
+      "loss": 2.1759,
+      "step": 7
+    },
+    {
+      "epoch": 0.0006315249353673699,
+      "grad_norm": 2.637096405029297,
+      "learning_rate": 0.00016,
+      "loss": 1.7298,
+      "step": 8
+    },
+    {
+      "epoch": 0.0007104655522882911,
+      "grad_norm": 2.800448417663574,
+      "learning_rate": 0.00018,
+      "loss": 2.2445,
+      "step": 9
+    },
+    {
+      "epoch": 0.0007104655522882911,
+      "eval_loss": 1.7051926851272583,
+      "eval_runtime": 1035.9377,
+      "eval_samples_per_second": 5.149,
+      "eval_steps_per_second": 2.574,
+      "step": 9
+    },
+    {
+      "epoch": 0.0007894061692092124,
+      "grad_norm": 3.807906150817871,
+      "learning_rate": 0.0002,
+      "loss": 2.1952,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -72,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2052393617326080.0,
+  "total_flos": 4104787234652160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null