Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e591311ba6884d878ad037145b9db8a0e02cb322a3315bba72952e92de0df5cf
+oid sha256:12a67b918ec83ab7425d638d6fade29fa527aa548c14e0edf1937e4ac252c9d6
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7c0dbf6366b380e05f915417c0cb3827f3bb93203112b1ced4fadd1be6c53fd
+oid sha256:b313d77671947acb5bd8acc8715ed392879628ed05dee616c7d189a7fd6b7306
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da70fcbf4bc000d633bdd59ff5bb75c3f527ccd5147f13a7552f0015370d4e68
+oid sha256:097784a8459b5523bce7987c706d00d9b0797f9210986fe9634a24ded975f97c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005684240443370754,
+  "epoch": 0.011368480886741509,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 17.034,
       "eval_steps_per_second": 8.528,
       "step": 10
+    },
+    {
+      "epoch": 0.006821088532044906,
+      "grad_norm": 1.4783978462219238,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2.3298,
+      "step": 12
+    },
+    {
+      "epoch": 0.008526360665056132,
+      "grad_norm": 1.7873011827468872,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.3034,
+      "step": 15
+    },
+    {
+      "epoch": 0.008526360665056132,
+      "eval_loss": 2.2579123973846436,
+      "eval_runtime": 43.5312,
+      "eval_samples_per_second": 17.022,
+      "eval_steps_per_second": 8.523,
+      "step": 15
+    },
+    {
+      "epoch": 0.010231632798067358,
+      "grad_norm": 1.354712963104248,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.0323,
+      "step": 18
+    },
+    {
+      "epoch": 0.011368480886741509,
+      "eval_loss": 2.1692159175872803,
+      "eval_runtime": 43.4964,
+      "eval_samples_per_second": 17.036,
+      "eval_steps_per_second": 8.529,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709436417802240.0,
+  "total_flos": 7511608746049536.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null