Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:675e0a3f6b6460103ecac01d077776ddfbebc062593723c781c6098af8ef86c1
+oid sha256:0b6c161634ef9071ce31fafc2f817dec8c4a627280fff737b86ddffe13cd651f
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ce121887d09ac7d8c8485e004576dfe91fd05aa5cb6bc6495d1bb22ed13c6a4
+oid sha256:7e78323e4f60a35fabce53f4ef2fbf296fd58158a7cf5e7761217fb2c5dfe94c
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e1abc6529582bc597a1cf37095dd09b36a6879413f7b6d8a94b140563ed578c
+oid sha256:8533ac5c809e23e45fa3502773ae0eeaf07bc3c38c0faa86616fda6bd7fa0465
 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": 0.06382978723404255,
+  "epoch": 0.1276595744680851,
   "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": 66.397,
       "eval_steps_per_second": 33.199,
       "step": 3
+    },
+    {
+      "epoch": 0.0851063829787234,
+      "grad_norm": 2.1976680755615234,
+      "learning_rate": 8e-05,
+      "loss": 3.7946,
+      "step": 4
+    },
+    {
+      "epoch": 0.10638297872340426,
+      "grad_norm": 2.464569330215454,
+      "learning_rate": 0.0001,
+      "loss": 3.6771,
+      "step": 5
+    },
+    {
+      "epoch": 0.1276595744680851,
+      "grad_norm": 3.11846661567688,
+      "learning_rate": 0.00012,
+      "loss": 4.2779,
+      "step": 6
+    },
+    {
+      "epoch": 0.1276595744680851,
+      "eval_loss": 3.676224946975708,
+      "eval_runtime": 0.3202,
+      "eval_samples_per_second": 62.46,
+      "eval_steps_per_second": 31.23,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 72163654631424.0,
+  "total_flos": 144327309262848.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null