Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:337d4d9062020c935a4512df42fa0eae4bc8726c42abfb339e5a3db2d2da460d
+oid sha256:860af7f59f0bb7511236cd4cffa6d9502cb9cca82d5d25e947b67aec557d2e96
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc25575b20ea9d87bdd9181c890fd7a174962d333f67ea0884246fbf183d529c
+oid sha256:dbff0a2488cd60a2dc59aa274e511151b01dfa31e027531070467d558a1d0d28
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d63550aef934dca682dbe4a2a94ff2b1a5fd333f064103ac7badea775ed97a9
+oid sha256:7a8fbdd40f7edc9d5266c41a92e911a33f810a381088729bf4c84d9fe8f8cfae
 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": 37.342,
       "eval_steps_per_second": 18.671,
       "step": 3
+    },
+    {
+      "epoch": 0.01871345029239766,
+      "grad_norm": 1.5755374431610107,
+      "learning_rate": 8e-05,
+      "loss": 1.0969,
+      "step": 4
+    },
+    {
+      "epoch": 0.023391812865497075,
+      "grad_norm": 1.0206433534622192,
+      "learning_rate": 0.0001,
+      "loss": 0.9503,
+      "step": 5
+    },
+    {
+      "epoch": 0.028070175438596492,
+      "grad_norm": 1.029083251953125,
+      "learning_rate": 0.00012,
+      "loss": 0.8455,
+      "step": 6
+    },
+    {
+      "epoch": 0.028070175438596492,
+      "eval_loss": 1.0448113679885864,
+      "eval_runtime": 2.4564,
+      "eval_samples_per_second": 36.639,
+      "eval_steps_per_second": 18.319,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 162531632480256.0,
+  "total_flos": 312560831692800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null