Training in progress, epoch 3, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:130a2d4195ddad291806770dd892fc49aaafbf5ec7e7907e00e75c68b7871d37
+oid sha256:b4f7252f604cf965972957c688430867f606aac2bec4eb77fb202768aa651f70
 size 218121344

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cea114f913608451f62d88f2a50125f9e41e93c364712f7a6cd8a7a03cb3b4cb
+oid sha256:5d1090523e29fc489b18443eb3a415b3bb5265e6129512691fad09e588f82982
 size 109417018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a2c5c8aad1f653aa3add540bd0333048434edf18474c9c3d336b12c1a0d72d1
+oid sha256:69a0a70cb7e3a876b8eb26e7da00ee587d5d1961bed884261da996978a8703fd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92bfc405766b86707d993d341611292e310f65cbbf495ba0d07d41a9098b0704
+oid sha256:578b41f9923ae9433bb17df44ecd934af6b2b0e1a29240e7817c1990bdf3b072
 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": 3054,
+  "global_step": 4581,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,111 @@
       "learning_rate": 0.0001833555259653795,
       "loss": 0.5619,
       "step": 3000
+    },
+    {
+      "epoch": 2.0301244269810086,
+      "grad_norm": 2.794207811355591,
+      "learning_rate": 0.00018268974700399467,
+      "loss": 0.4983,
+      "step": 3100
+    },
+    {
+      "epoch": 2.0956123117223315,
+      "grad_norm": 1.3407844305038452,
+      "learning_rate": 0.00018202396804260987,
+      "loss": 0.4355,
+      "step": 3200
+    },
+    {
+      "epoch": 2.161100196463654,
+      "grad_norm": 1.74431312084198,
+      "learning_rate": 0.00018135818908122505,
+      "loss": 0.4409,
+      "step": 3300
+    },
+    {
+      "epoch": 2.226588081204977,
+      "grad_norm": 1.806471347808838,
+      "learning_rate": 0.00018069241011984023,
+      "loss": 0.4017,
+      "step": 3400
+    },
+    {
+      "epoch": 2.2920759659463,
+      "grad_norm": 2.9647037982940674,
+      "learning_rate": 0.0001800266311584554,
+      "loss": 0.4382,
+      "step": 3500
+    },
+    {
+      "epoch": 2.357563850687623,
+      "grad_norm": 1.1686805486679077,
+      "learning_rate": 0.00017936085219707058,
+      "loss": 0.4374,
+      "step": 3600
+    },
+    {
+      "epoch": 2.423051735428946,
+      "grad_norm": 1.3478459119796753,
+      "learning_rate": 0.00017869507323568575,
+      "loss": 0.4601,
+      "step": 3700
+    },
+    {
+      "epoch": 2.4885396201702683,
+      "grad_norm": 1.657325267791748,
+      "learning_rate": 0.00017802929427430096,
+      "loss": 0.4264,
+      "step": 3800
+    },
+    {
+      "epoch": 2.5540275049115913,
+      "grad_norm": 1.9698008298873901,
+      "learning_rate": 0.00017736351531291613,
+      "loss": 0.4012,
+      "step": 3900
+    },
+    {
+      "epoch": 2.619515389652914,
+      "grad_norm": 1.1528823375701904,
+      "learning_rate": 0.0001766977363515313,
+      "loss": 0.421,
+      "step": 4000
+    },
+    {
+      "epoch": 2.685003274394237,
+      "grad_norm": 1.4447120428085327,
+      "learning_rate": 0.00017603195739014649,
+      "loss": 0.414,
+      "step": 4100
+    },
+    {
+      "epoch": 2.75049115913556,
+      "grad_norm": 1.054911494255066,
+      "learning_rate": 0.00017536617842876166,
+      "loss": 0.4084,
+      "step": 4200
+    },
+    {
+      "epoch": 2.815979043876883,
+      "grad_norm": 3.767080307006836,
+      "learning_rate": 0.00017470039946737684,
+      "loss": 0.4556,
+      "step": 4300
+    },
+    {
+      "epoch": 2.8814669286182055,
+      "grad_norm": 3.200798749923706,
+      "learning_rate": 0.00017403462050599201,
+      "loss": 0.4421,
+      "step": 4400
+    },
+    {
+      "epoch": 2.9469548133595285,
+      "grad_norm": 1.371512532234192,
+      "learning_rate": 0.0001733688415446072,
+      "loss": 0.4335,
+      "step": 4500
     }
   ],
   "logging_steps": 100,
@@ -236,7 +341,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.149819657650176e+16,
+  "total_flos": 1.7247294894112768e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null