Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7198b4843d621cef8a973d89ce4f9984d0671ce161567215564f115624db9e4
+oid sha256:0cdd8d32fe8db2e7036505ccafee8b112a8cf127d08e0aa20486b07704ae38b6
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e87e5d1396879ff0b15ef7f4daa36d636a712251b6364ed7a64b7c9f096016ae
+oid sha256:db337792f3900c3200d5539a00f1a312565617ac5d19d54d2a57d8b30f28ce8b
 size 1001863522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bdb274779f011b606d8570dbe68b58aa7676941996afa7b13ca0369675c4ce6
+oid sha256:e04648c773506fe827721155d97cf3bf4c732c1876f34c64b43b79384bacc356
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00878464444151623,
+  "epoch": 0.01756928888303246,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 3.899,
       "eval_steps_per_second": 1.95,
       "step": 25
+    },
+    {
+      "epoch": 0.00913603021917688,
+      "grad_norm": 1.6291801929473877,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 7.8515,
+      "step": 26
+    },
+    {
+      "epoch": 0.009487415996837528,
+      "grad_norm": 1.4865143299102783,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 6.6876,
+      "step": 27
+    },
+    {
+      "epoch": 0.009838801774498177,
+      "grad_norm": 1.633550763130188,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 9.7649,
+      "step": 28
+    },
+    {
+      "epoch": 0.010190187552158827,
+      "grad_norm": 1.6559158563613892,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 7.7611,
+      "step": 29
+    },
+    {
+      "epoch": 0.010541573329819476,
+      "grad_norm": 1.56125807762146,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 8.1391,
+      "step": 30
+    },
+    {
+      "epoch": 0.010892959107480124,
+      "grad_norm": 1.4842593669891357,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 7.1128,
+      "step": 31
+    },
+    {
+      "epoch": 0.011244344885140775,
+      "grad_norm": 1.9677858352661133,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 8.2545,
+      "step": 32
+    },
+    {
+      "epoch": 0.011595730662801423,
+      "grad_norm": 2.1278786659240723,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 8.5091,
+      "step": 33
+    },
+    {
+      "epoch": 0.011947116440462072,
+      "grad_norm": 1.7648427486419678,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 6.5063,
+      "step": 34
+    },
+    {
+      "epoch": 0.01229850221812272,
+      "grad_norm": 1.6439030170440674,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 8.567,
+      "step": 35
+    },
+    {
+      "epoch": 0.012649887995783371,
+      "grad_norm": 1.884887456893921,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 8.3356,
+      "step": 36
+    },
+    {
+      "epoch": 0.01300127377344402,
+      "grad_norm": 1.6573904752731323,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 7.9903,
+      "step": 37
+    },
+    {
+      "epoch": 0.013352659551104668,
+      "grad_norm": 1.8767001628875732,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 7.5882,
+      "step": 38
+    },
+    {
+      "epoch": 0.013704045328765319,
+      "grad_norm": 2.158738374710083,
+      "learning_rate": 5e-05,
+      "loss": 9.144,
+      "step": 39
+    },
+    {
+      "epoch": 0.014055431106425967,
+      "grad_norm": 2.622767448425293,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 9.0718,
+      "step": 40
+    },
+    {
+      "epoch": 0.014406816884086616,
+      "grad_norm": 2.098249912261963,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 7.5903,
+      "step": 41
+    },
+    {
+      "epoch": 0.014758202661747266,
+      "grad_norm": 2.695885419845581,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 9.2641,
+      "step": 42
+    },
+    {
+      "epoch": 0.015109588439407915,
+      "grad_norm": 2.7287509441375732,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 9.99,
+      "step": 43
+    },
+    {
+      "epoch": 0.015460974217068563,
+      "grad_norm": 2.987199068069458,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 9.1632,
+      "step": 44
+    },
+    {
+      "epoch": 0.015812359994729214,
+      "grad_norm": 3.6520209312438965,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3929,
+      "step": 45
+    },
+    {
+      "epoch": 0.016163745772389864,
+      "grad_norm": 3.4548537731170654,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 10.003,
+      "step": 46
+    },
+    {
+      "epoch": 0.01651513155005051,
+      "grad_norm": 5.150744915008545,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 11.3511,
+      "step": 47
+    },
+    {
+      "epoch": 0.01686651732771116,
+      "grad_norm": 7.644892692565918,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.2625,
+      "step": 48
+    },
+    {
+      "epoch": 0.01721790310537181,
+      "grad_norm": 9.981356620788574,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 11.0407,
+      "step": 49
+    },
+    {
+      "epoch": 0.01756928888303246,
+      "grad_norm": 21.54275131225586,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 13.8822,
+      "step": 50
+    },
+    {
+      "epoch": 0.01756928888303246,
+      "eval_loss": 1.019070029258728,
+      "eval_runtime": 614.5764,
+      "eval_samples_per_second": 3.9,
+      "eval_steps_per_second": 1.951,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.781883052032e+16,
+  "total_flos": 1.4160475717632e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null