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:c9825e017f5f8f35079c483ec945bd8b08c7707c2d1624bae9f56f560cbb4898
+oid sha256:344fe5b1ab436b4e159bb660aed23d95cc14dd202369d5fea2933442d99d9ef2
 size 30322120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd3b1b93c7bd98103fe2cb8ed03f11fddba0caf01e5e2a746be1d91efbd612e1
+oid sha256:888c530a8956ee847fd63375230545890976feeebc9c90be2c8f751b7aa819ed
 size 15768084

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3553675b78bc944ecd3ec0c4e337162ea0509a1705ab7c9e99a57cb85e7b9e4b
+oid sha256:a4cd63e5854d7608ff9b84a573f42d28e6f0b2b619715d4fbf125bb8c3722858
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ed01d5bf56e0e105c87c31bc7cdc5697fc2cafe3fc41c19235046052b8cdd70
+oid sha256:b0382479da225f070cb1faebc05470f4816121d372788b28762c19044ea4f670
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01e56ab0605b929b82207b7904a55712db330eec5b9112314d048a09ac7d2f40
+oid sha256:b9d7cf78e23cea6ea1fb0e37a19f5cdd148e6fcc4573057e394e98a8ada5b12c
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ff58d8cfe8ffe8735fecf0dcc09939a77928ad93be623f59fa8e9e6c2a331b4
+oid sha256:6f19589351eb4c0a21083c28d2746788bf4ffeb13b476eb758a386035199fe9a
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:064d24b8cde6867bcb8a58fcd1e05ed8f6d5c126d3d8ca548e250a6641d6fa29
+oid sha256:b1e9830a62ca8dc0c158eabc2170cfe5b3e4d45c94a2de9cd6ae2edf3fadc0f4
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49d34daea1dcf6e53396de418cae0068b0c083f9560f9e59f3bf8d9152b5ba05
+oid sha256:f23c1d91069a21f7fe802606cd7abe02d88fe1e12ce6fc5cc340ac8bbef346af
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e97809cc1ff29cda56456b3608043c5d0693e80228358b096a365c44c54b702
+oid sha256:71ce565e4acf9f01c116c60a060c66b98f6ad793eb6ee4d27f31fe6deebcb6bd
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39df6a0a5381eb615ded39fbf554fd480616f42372073f82877b7639d4d4b0b8
+oid sha256:3c040daa9b9a86d2b1b67b2963865ec80bd2eada416fde3aef17b1c678661296
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0821917808219178,
+  "epoch": 0.1232876712328767,
   "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": 98.297,
       "eval_steps_per_second": 12.787,
       "step": 6
+    },
+    {
+      "epoch": 0.0958904109589041,
+      "grad_norm": 10.823620796203613,
+      "learning_rate": 8e-05,
+      "loss": 4.4948,
+      "step": 7
+    },
+    {
+      "epoch": 0.1095890410958904,
+      "grad_norm": 10.48684024810791,
+      "learning_rate": 0.0001,
+      "loss": 3.8815,
+      "step": 8
+    },
+    {
+      "epoch": 0.1232876712328767,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 3.2615,
+      "step": 9
+    },
+    {
+      "epoch": 0.1232876712328767,
+      "eval_loss": 3.383413553237915,
+      "eval_runtime": 1.2385,
+      "eval_samples_per_second": 99.313,
+      "eval_steps_per_second": 12.919,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1490955484004352.0,
+  "total_flos": 2236433226006528.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null