Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:344fe5b1ab436b4e159bb660aed23d95cc14dd202369d5fea2933442d99d9ef2
+oid sha256:4facdd32a42c16006abf864c95d0c0a4954419c88e25d8b600872ce8c7d464c5
 size 30322120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:888c530a8956ee847fd63375230545890976feeebc9c90be2c8f751b7aa819ed
+oid sha256:f116acd89dae052f04248e67a2832d416d193026999e13d8e0ddbc521751156b
 size 15768084

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4cd63e5854d7608ff9b84a573f42d28e6f0b2b619715d4fbf125bb8c3722858
+oid sha256:35b0aa6cb70607f993a88333de2f1dacfcd98306994cc9843da7f3e61f4d6d91
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0382479da225f070cb1faebc05470f4816121d372788b28762c19044ea4f670
+oid sha256:a8e8954d1428b7e404e0ca3b21e72c15809e3a97f9e9a3e522a4cb7022664755
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9d7cf78e23cea6ea1fb0e37a19f5cdd148e6fcc4573057e394e98a8ada5b12c
+oid sha256:17c2e9a36c1816fd251b73ae45fc052ee5e7fd9acfc9bd2c71ff9bbdafbe01c2
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f19589351eb4c0a21083c28d2746788bf4ffeb13b476eb758a386035199fe9a
+oid sha256:177889298276f824edaa2975d34c49c3b87826602ed968113f44c41c5c0d77e4
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1e9830a62ca8dc0c158eabc2170cfe5b3e4d45c94a2de9cd6ae2edf3fadc0f4
+oid sha256:8272a8ae7253af9a8455ea73a52832cb46f81796cb4f8ee8d42bbe3c3947ad3b
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23c1d91069a21f7fe802606cd7abe02d88fe1e12ce6fc5cc340ac8bbef346af
+oid sha256:4e4d79225c69fab4bcd3055bb006c2b5fe62ac285c5b0dce376292249e92e5bd
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71ce565e4acf9f01c116c60a060c66b98f6ad793eb6ee4d27f31fe6deebcb6bd
+oid sha256:01a297d3d14f4f460a76f07e1930748f639e3c5f02b025148c0028451aad141a
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c040daa9b9a86d2b1b67b2963865ec80bd2eada416fde3aef17b1c678661296
+oid sha256:d5337339b6310dbf1d5aa88f4425d6e1769cb673a3215ad52354879b2451319d
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1232876712328767,
+  "epoch": 0.136986301369863,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 99.313,
       "eval_steps_per_second": 12.919,
       "step": 9
+    },
+    {
+      "epoch": 0.136986301369863,
+      "grad_norm": 10.866177558898926,
+      "learning_rate": 0.00012,
+      "loss": 3.3794,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2236433226006528.0,
+  "total_flos": 2484925806673920.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null