Training in progress, epoch 3, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6782df2f2db0ac7bbc134ad906573e8638b47f75a95fee0a2bfe7f386f13d0da
+oid sha256:485b1aeb8375edbfaf998dc6e904cb1be230788d7cf32acfec654b805e1aab8f
 size 389074464

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbf98f1f34561d3270b88b660f3acffab2e9f52fe2624015066c24343b00468a
+oid sha256:51e628ac394e2249e6425baad917a19fc3fb7e32adab3521dc1c60bd4a5b0b6a
 size 198011700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11956a942606994fa76d833e8e9e90648747b2b0ea23a5faea758aaa1e572ea6
+oid sha256:336ad624cfb7adf5821759ee06496a34d9d2a658dd99d3dbdda29b76da15094d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 1046,
+  "global_step": 1569,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,41 @@
       "learning_rate": 4.083011583011583e-05,
       "loss": 0.7385,
       "step": 1000
+    },
+    {
+      "epoch": 2.1032504780114722,
+      "grad_norm": 0.9055523872375488,
+      "learning_rate": 3.986486486486487e-05,
+      "loss": 0.6388,
+      "step": 1100
+    },
+    {
+      "epoch": 2.294455066921606,
+      "grad_norm": 1.2273402214050293,
+      "learning_rate": 3.8899613899613905e-05,
+      "loss": 0.5685,
+      "step": 1200
+    },
+    {
+      "epoch": 2.48565965583174,
+      "grad_norm": 1.0323429107666016,
+      "learning_rate": 3.7934362934362935e-05,
+      "loss": 0.5597,
+      "step": 1300
+    },
+    {
+      "epoch": 2.676864244741874,
+      "grad_norm": 0.9804114699363708,
+      "learning_rate": 3.696911196911197e-05,
+      "loss": 0.6144,
+      "step": 1400
+    },
+    {
+      "epoch": 2.8680688336520075,
+      "grad_norm": 0.6983469724655151,
+      "learning_rate": 3.6003861003861e-05,
+      "loss": 0.5832,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
@@ -96,7 +131,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.70116458564608e+16,
+  "total_flos": 8.55174687846912e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null