Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4af87b10825675ac565615b8b4f382c58ee26e1194b8d4f397e2c074e05aa2fa
+oid sha256:c9825e017f5f8f35079c483ec945bd8b08c7707c2d1624bae9f56f560cbb4898
 size 30322120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:865834f3149440e2c81cf5e54f5a11e8153d3126739eb387105def0a81fb0747
-size 1960
+oid sha256:fd3b1b93c7bd98103fe2cb8ed03f11fddba0caf01e5e2a746be1d91efbd612e1
+size 15768084

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1899d099ba864daa2e52d92d060c874579a9cfc6391a138cfe4c80e9b13d9f19
+oid sha256:3553675b78bc944ecd3ec0c4e337162ea0509a1705ab7c9e99a57cb85e7b9e4b
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33a325a3d37578e98840bb9224fed0b1604a037fb7bb865cba8dac640768ad5f
+oid sha256:2ed01d5bf56e0e105c87c31bc7cdc5697fc2cafe3fc41c19235046052b8cdd70
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa8f3de397a9d6207e641f470691320e10a46a5e8a51802eb84e7afa489a7071
+oid sha256:01e56ab0605b929b82207b7904a55712db330eec5b9112314d048a09ac7d2f40
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74646f87957e0b806cb9dc4ced64aacc30204c98160e9122ee720aa0703b923a
+oid sha256:4ff58d8cfe8ffe8735fecf0dcc09939a77928ad93be623f59fa8e9e6c2a331b4
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31aa36e609fe266f60072fc9ad3cbcd379c875761af48e32294980c65c1140d7
+oid sha256:064d24b8cde6867bcb8a58fcd1e05ed8f6d5c126d3d8ca548e250a6641d6fa29
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba222ee5f1507f0c0b6d2b9e1b20b7896bfaef2c8fa6f139720adfa0dcc84b3
+oid sha256:49d34daea1dcf6e53396de418cae0068b0c083f9560f9e59f3bf8d9152b5ba05
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e948dad35f8562a98663e1b2fb153250f1cf155d9cbdf87d044786d385930f3
+oid sha256:6e97809cc1ff29cda56456b3608043c5d0693e80228358b096a365c44c54b702
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32eceaf1ba02ee3619fd6b94cbedebf3d6ebffe8c01dc3eef88f37a684d0308f
+oid sha256:39df6a0a5381eb615ded39fbf554fd480616f42372073f82877b7639d4d4b0b8
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:219c62af0a99d0a3db4c57e4189ef3b142499e30571ad5cc800b8b67c9ce1583
+oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0410958904109589,
+  "epoch": 0.0821917808219178,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 97.721,
       "eval_steps_per_second": 12.712,
       "step": 3
+    },
+    {
+      "epoch": 0.0547945205479452,
+      "grad_norm": 10.800760269165039,
+      "learning_rate": 2e-05,
+      "loss": 4.8914,
+      "step": 4
+    },
+    {
+      "epoch": 0.0684931506849315,
+      "grad_norm": 12.797863006591797,
+      "learning_rate": 4e-05,
+      "loss": 5.0571,
+      "step": 5
+    },
+    {
+      "epoch": 0.0821917808219178,
+      "grad_norm": 11.154678344726562,
+      "learning_rate": 6e-05,
+      "loss": 4.6968,
+      "step": 6
+    },
+    {
+      "epoch": 0.0821917808219178,
+      "eval_loss": 4.427567958831787,
+      "eval_runtime": 1.2513,
+      "eval_samples_per_second": 98.297,
+      "eval_steps_per_second": 12.787,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 745477742002176.0,
+  "total_flos": 1490955484004352.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null