Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ab49a3e648e9ebd4db0b5a96fa5cf6e268efc806ad2232c0677ef26bc4e651b
+oid sha256:26d453fe1225729173a9ec91012af2f0c26c851e616c31691db22524ef3a9f3b
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:357087a5948da7ee9b39cd69083864e872495027a9efceceb415ee0efa2d587d
+oid sha256:34bbb6c1ebd8aba9cec0010a32ad5ebdd6e4fb519c643e061d98c446427a990d
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1919048fff6416e881e72f2bd47c9e50bdfb63dab1663fa38ff5bebaa67abda9
+oid sha256:7fa5a9e7fe9b733f4d7378c2f4295e39738bd784ce49157561d991d047aeb2c0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014035087719298246,
+  "epoch": 0.028070175438596492,
   "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": 22.628,
       "eval_steps_per_second": 11.314,
       "step": 3
+    },
+    {
+      "epoch": 0.01871345029239766,
+      "grad_norm": 1.2403775453567505,
+      "learning_rate": 8e-05,
+      "loss": 3.0677,
+      "step": 4
+    },
+    {
+      "epoch": 0.023391812865497075,
+      "grad_norm": 1.1208009719848633,
+      "learning_rate": 0.0001,
+      "loss": 2.9597,
+      "step": 5
+    },
+    {
+      "epoch": 0.028070175438596492,
+      "grad_norm": 1.4384738206863403,
+      "learning_rate": 0.00012,
+      "loss": 2.9013,
+      "step": 6
+    },
+    {
+      "epoch": 0.028070175438596492,
+      "eval_loss": 0.7677449584007263,
+      "eval_runtime": 4.0343,
+      "eval_samples_per_second": 22.309,
+      "eval_steps_per_second": 11.154,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 436027854422016.0,
+  "total_flos": 895004543287296.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null