Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b51edb95931c50c7eccffe73d0c373447c32b5551b695812216e3bd9d18b2928
+oid sha256:e66a2dd8d3d2bbed1d876000dda0651212a54ba174dc9b3cd15e946adefaca8f
 size 36220072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:481a7a996369d8d39cb2ff983ba7d20de9cdb194073610ec25fb97d5046a40c3
-size 18763860
+oid sha256:75a9067022dd03df96d0f89703e9bc525a8489b35c83eb6ec203a92f4ee520a9
+size 18764180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba08bf9c96258aa66309cebbe094ba794b566e771cd04cb308d30904cb3fcb21
+oid sha256:652624241b697f848aa0b96d2618afbd1e071c5dbd47f895da652fcde2a22b64
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ac116b8169c53ab649a7f15f2f32735f2c71ec2f803f70de8c655a513ee9cfc
+oid sha256:43da0688aca60835f4e18fa7e0f3cc099504828f82fd5dd994118be26b760a0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.032609138711123795,
+  "epoch": 0.04891370806668569,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -311,6 +311,154 @@
       "eval_samples_per_second": 25.274,
       "eval_steps_per_second": 12.642,
       "step": 200
+    },
+    {
+      "epoch": 0.03342436717890189,
+      "grad_norm": 0.18553270399570465,
+      "learning_rate": 5e-05,
+      "loss": 0.6936,
+      "step": 205
+    },
+    {
+      "epoch": 0.034239595646679985,
+      "grad_norm": 0.1617966592311859,
+      "learning_rate": 4.798670299452926e-05,
+      "loss": 0.7387,
+      "step": 210
+    },
+    {
+      "epoch": 0.03505482411445808,
+      "grad_norm": 0.23151330649852753,
+      "learning_rate": 4.597667156416371e-05,
+      "loss": 0.6698,
+      "step": 215
+    },
+    {
+      "epoch": 0.03587005258223617,
+      "grad_norm": 0.172349214553833,
+      "learning_rate": 4.397316598723385e-05,
+      "loss": 0.6974,
+      "step": 220
+    },
+    {
+      "epoch": 0.036685281050014264,
+      "grad_norm": 0.15773482620716095,
+      "learning_rate": 4.197943595711198e-05,
+      "loss": 0.7278,
+      "step": 225
+    },
+    {
+      "epoch": 0.03750050951779236,
+      "grad_norm": 0.1810629963874817,
+      "learning_rate": 3.9998715311197785e-05,
+      "loss": 0.6484,
+      "step": 230
+    },
+    {
+      "epoch": 0.038315737985570454,
+      "grad_norm": 0.18713156878948212,
+      "learning_rate": 3.803421678562213e-05,
+      "loss": 0.684,
+      "step": 235
+    },
+    {
+      "epoch": 0.03913096645334855,
+      "grad_norm": 0.25403130054473877,
+      "learning_rate": 3.608912680417737e-05,
+      "loss": 0.7086,
+      "step": 240
+    },
+    {
+      "epoch": 0.039946194921126645,
+      "grad_norm": 0.15474697947502136,
+      "learning_rate": 3.4166600309926387e-05,
+      "loss": 0.6171,
+      "step": 245
+    },
+    {
+      "epoch": 0.04076142338890474,
+      "grad_norm": 0.17823943495750427,
+      "learning_rate": 3.226975564787322e-05,
+      "loss": 0.6566,
+      "step": 250
+    },
+    {
+      "epoch": 0.041576651856682835,
+      "grad_norm": 0.34823134541511536,
+      "learning_rate": 3.0401669506996256e-05,
+      "loss": 0.6684,
+      "step": 255
+    },
+    {
+      "epoch": 0.04239188032446093,
+      "grad_norm": 0.15805622935295105,
+      "learning_rate": 2.8565371929847284e-05,
+      "loss": 0.6549,
+      "step": 260
+    },
+    {
+      "epoch": 0.043207108792239025,
+      "grad_norm": 0.13102880120277405,
+      "learning_rate": 2.6763841397811573e-05,
+      "loss": 0.6221,
+      "step": 265
+    },
+    {
+      "epoch": 0.04402233726001712,
+      "grad_norm": 0.15072394907474518,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.699,
+      "step": 270
+    },
+    {
+      "epoch": 0.044837565727795216,
+      "grad_norm": 0.18680483102798462,
+      "learning_rate": 2.3276708693609943e-05,
+      "loss": 0.7056,
+      "step": 275
+    },
+    {
+      "epoch": 0.04565279419557331,
+      "grad_norm": 0.19171744585037231,
+      "learning_rate": 2.1596762663442218e-05,
+      "loss": 0.6821,
+      "step": 280
+    },
+    {
+      "epoch": 0.046468022663351406,
+      "grad_norm": 0.2306189388036728,
+      "learning_rate": 1.996288678810105e-05,
+      "loss": 0.725,
+      "step": 285
+    },
+    {
+      "epoch": 0.0472832511311295,
+      "grad_norm": 0.2382626235485077,
+      "learning_rate": 1.837773122023114e-05,
+      "loss": 0.7041,
+      "step": 290
+    },
+    {
+      "epoch": 0.0480984795989076,
+      "grad_norm": 0.2878624498844147,
+      "learning_rate": 1.684386708796025e-05,
+      "loss": 0.7284,
+      "step": 295
+    },
+    {
+      "epoch": 0.04891370806668569,
+      "grad_norm": 0.2006363421678543,
+      "learning_rate": 1.536378232452003e-05,
+      "loss": 0.7574,
+      "step": 300
+    },
+    {
+      "epoch": 0.04891370806668569,
+      "eval_loss": 0.7295248508453369,
+      "eval_runtime": 102.1368,
+      "eval_samples_per_second": 25.29,
+      "eval_steps_per_second": 12.65,
+      "step": 300
     }
   ],
   "logging_steps": 5,
@@ -330,7 +478,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8669553072472064e+16,
+  "total_flos": 2.808394390752461e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null