Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44356bc3a548670347cdc5de3470da1bd1c8296056c9936a92819d3e72f70179
+oid sha256:c1b2c7e01260fa2d76e74a450b8b2504c0cd038b513946673dcc793bf350a8b9
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9714b102d946a2416661f396fb73712740ee3fb3f6f925b59c4b18b9640be6e
+oid sha256:28ef3294a582065127c0779372304455d587e1c5d7d390b662b394065b0872b0
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92c7e8ba47a91f7c3a8e5edb58267bf5e0f66e3e84786059780fd648ecff005d
+oid sha256:eedb2a7e70cd3ddb5e4b069afa99ed1d476536fe99262e3af8da16dc7f01adbf
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ab1a35a51dfbc38a10e69b1dd8572b85254ecc3fb61f9c5293b55135da596f8
+oid sha256:47e1693efd3253b65c059352e1453da814f21eb02ddf59e0d5b362c9c1691055
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0022500984418068293,
+  "epoch": 0.0045001968836136585,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 11.11,
       "eval_steps_per_second": 2.778,
       "step": 5
+    },
+    {
+      "epoch": 0.002700118130168195,
+      "grad_norm": 0.23115503787994385,
+      "learning_rate": 6e-05,
+      "loss": 0.5711,
+      "step": 6
+    },
+    {
+      "epoch": 0.003150137818529561,
+      "grad_norm": 0.25062692165374756,
+      "learning_rate": 7e-05,
+      "loss": 0.6868,
+      "step": 7
+    },
+    {
+      "epoch": 0.0036001575068909265,
+      "grad_norm": 0.21780619025230408,
+      "learning_rate": 8e-05,
+      "loss": 0.6653,
+      "step": 8
+    },
+    {
+      "epoch": 0.004050177195252292,
+      "grad_norm": 0.21652354300022125,
+      "learning_rate": 9e-05,
+      "loss": 0.606,
+      "step": 9
+    },
+    {
+      "epoch": 0.0045001968836136585,
+      "grad_norm": 0.2677552402019501,
+      "learning_rate": 0.0001,
+      "loss": 0.6374,
+      "step": 10
+    },
+    {
+      "epoch": 0.0045001968836136585,
+      "eval_loss": 0.6517220735549927,
+      "eval_runtime": 1347.593,
+      "eval_samples_per_second": 11.109,
+      "eval_steps_per_second": 2.778,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1870196536967168e+17,
+  "total_flos": 2.3740393073934336e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null