Training in progress, epoch 3, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d37129b48e7417e0dfeb501a27c3a294b2d23ccd53a2d46aee9a82c4355cce4
+oid sha256:674201cda7990812ad89a0ac22c31df0b82d264ffcdd8a5bdb1dd62baf293d81
 size 389074464

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5e1907216e4e70e553b298348137c55ab7915ccdbf957f9e97bcd5a2584c0e7
+oid sha256:93975c5b076ce7d294a4f8acb8ef330cf5533dda15b666fec59a388f8c4aa1a9
 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": 0.9010747671127319,
+      "learning_rate": 3.986486486486487e-05,
+      "loss": 0.6386,
+      "step": 1100
+    },
+    {
+      "epoch": 2.294455066921606,
+      "grad_norm": 1.2023605108261108,
+      "learning_rate": 3.8899613899613905e-05,
+      "loss": 0.5685,
+      "step": 1200
+    },
+    {
+      "epoch": 2.48565965583174,
+      "grad_norm": 1.032483458518982,
+      "learning_rate": 3.7934362934362935e-05,
+      "loss": 0.5601,
+      "step": 1300
+    },
+    {
+      "epoch": 2.676864244741874,
+      "grad_norm": 0.979926347732544,
+      "learning_rate": 3.696911196911197e-05,
+      "loss": 0.6145,
+      "step": 1400
+    },
+    {
+      "epoch": 2.8680688336520075,
+      "grad_norm": 0.6987595558166504,
+      "learning_rate": 3.6003861003861e-05,
+      "loss": 0.5834,
+      "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