Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71bc098a8275113c28a780410aff9f5ccce9c64d8ece24bf261f6d3a460df248
+oid sha256:eada732e346e878e42c7d8fa75b9f0172115415614d3764563c15a5d9e64e7ff
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eea78bd04faabc84449313a3b21644c8a2cbd1cf5eebe2e76bb06c90d52610f9
+oid sha256:0a826e40b0b99b1a035c9ad5844aeb6bd779e310329dc9a9084ed12391aaa2dd
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c99adfd3842a16f78adc954f43d1319a31e4bf74797a8fd450f6ab3f8c288b
+oid sha256:0c325a5b88aa7600e783ee566917eff9758a4ec707c33c129463258bf687aee2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:842484d97bbf42f9f92b7e7c8dcf4fda5e0b0607fec45e60ed168e6d3a7f3132
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001266490765171504,
+  "epoch": 0.0016886543535620053,
   "eval_steps": 3,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,49 @@
       "eval_samples_per_second": 11.813,
       "eval_steps_per_second": 5.908,
       "step": 15
+    },
+    {
+      "epoch": 0.0013509234828496042,
+      "grad_norm": 9.136611938476562,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.2849,
+      "step": 16
+    },
+    {
+      "epoch": 0.0014353562005277045,
+      "grad_norm": 7.953118324279785,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.1662,
+      "step": 17
+    },
+    {
+      "epoch": 0.0015197889182058048,
+      "grad_norm": 2.821458578109741,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.0864,
+      "step": 18
+    },
+    {
+      "epoch": 0.0015197889182058048,
+      "eval_loss": 0.24295015633106232,
+      "eval_runtime": 422.3791,
+      "eval_samples_per_second": 11.807,
+      "eval_steps_per_second": 5.905,
+      "step": 18
+    },
+    {
+      "epoch": 0.001604221635883905,
+      "grad_norm": 1.723188042640686,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.044,
+      "step": 19
+    },
+    {
+      "epoch": 0.0016886543535620053,
+      "grad_norm": 6.9622321128845215,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1891,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -179,7 +222,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5548692744437760.0,
+  "total_flos": 7398256992583680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null