Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:822c578f50f300ceeb35d1c3b82df3d82e7f81f6d7fd5c0daf65dd176a69078a
+oid sha256:5e0e653f05533806fdb05b659c8f7052ec02659f7f0c2d8357852523fb230559
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da59b0cebc254da91420c8d630b99628027a2658f1baee38f40b706d4a9e746d
+oid sha256:35c5297c90fb5bc540ca1e62a87631dee45fb38bba5aebaa94f442a62ac3d4d3
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b39a79df42874b54e01731649d4c9656970ca1cb57dc8dfa52f950eff5cbdb5
+oid sha256:42f16f8966b76b56247bfdbba540fb56fae433750733d692ba4648ccdae3bdfd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0021329920546045967,
+  "epoch": 0.003199488081906895,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 5.898,
       "eval_steps_per_second": 2.949,
       "step": 50
+    },
+    {
+      "epoch": 0.0021756518956966885,
+      "grad_norm": 2.0142173767089844,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.9362,
+      "step": 51
+    },
+    {
+      "epoch": 0.0022183117367887803,
+      "grad_norm": 2.2668869495391846,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 2.5948,
+      "step": 52
+    },
+    {
+      "epoch": 0.0022609715778808726,
+      "grad_norm": 2.5661771297454834,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 3.2879,
+      "step": 53
+    },
+    {
+      "epoch": 0.0023036314189729644,
+      "grad_norm": 2.1952974796295166,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.054,
+      "step": 54
+    },
+    {
+      "epoch": 0.002346291260065056,
+      "grad_norm": 2.2668612003326416,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 3.2251,
+      "step": 55
+    },
+    {
+      "epoch": 0.002388951101157148,
+      "grad_norm": 1.8296819925308228,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 2.4021,
+      "step": 56
+    },
+    {
+      "epoch": 0.0024316109422492403,
+      "grad_norm": 2.153315782546997,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.4252,
+      "step": 57
+    },
+    {
+      "epoch": 0.002474270783341332,
+      "grad_norm": 2.292271614074707,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 2.3999,
+      "step": 58
+    },
+    {
+      "epoch": 0.002516930624433424,
+      "grad_norm": 1.9195157289505005,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.5964,
+      "step": 59
+    },
+    {
+      "epoch": 0.0025595904655255157,
+      "grad_norm": 1.9605921506881714,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.3407,
+      "step": 60
+    },
+    {
+      "epoch": 0.002602250306617608,
+      "grad_norm": 1.9012995958328247,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 2.368,
+      "step": 61
+    },
+    {
+      "epoch": 0.0026449101477097,
+      "grad_norm": 1.9466537237167358,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 2.4592,
+      "step": 62
+    },
+    {
+      "epoch": 0.0026875699888017916,
+      "grad_norm": 1.8879311084747314,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.9293,
+      "step": 63
+    },
+    {
+      "epoch": 0.0027302298298938835,
+      "grad_norm": 1.9396064281463623,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 2.0808,
+      "step": 64
+    },
+    {
+      "epoch": 0.0027728896709859757,
+      "grad_norm": 2.0695531368255615,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 2.8054,
+      "step": 65
+    },
+    {
+      "epoch": 0.0028155495120780675,
+      "grad_norm": 2.0114097595214844,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.7048,
+      "step": 66
+    },
+    {
+      "epoch": 0.0028582093531701594,
+      "grad_norm": 2.431223154067993,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 3.0252,
+      "step": 67
+    },
+    {
+      "epoch": 0.002900869194262251,
+      "grad_norm": 2.1020631790161133,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 2.7235,
+      "step": 68
+    },
+    {
+      "epoch": 0.0029435290353543434,
+      "grad_norm": 2.0261971950531006,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.4901,
+      "step": 69
+    },
+    {
+      "epoch": 0.0029861888764464353,
+      "grad_norm": 2.127995729446411,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 2.7434,
+      "step": 70
+    },
+    {
+      "epoch": 0.003028848717538527,
+      "grad_norm": 1.97040855884552,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 3.0585,
+      "step": 71
+    },
+    {
+      "epoch": 0.003071508558630619,
+      "grad_norm": 1.9737168550491333,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.5883,
+      "step": 72
+    },
+    {
+      "epoch": 0.003114168399722711,
+      "grad_norm": 2.150047540664673,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 3.1533,
+      "step": 73
+    },
+    {
+      "epoch": 0.003156828240814803,
+      "grad_norm": 2.6070427894592285,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 2.7457,
+      "step": 74
+    },
+    {
+      "epoch": 0.003199488081906895,
+      "grad_norm": 2.3490138053894043,
+      "learning_rate": 0.0,
+      "loss": 2.8359,
+      "step": 75
+    },
+    {
+      "epoch": 0.003199488081906895,
+      "eval_loss": 0.3554416000843048,
+      "eval_runtime": 3346.2309,
+      "eval_samples_per_second": 5.899,
+      "eval_steps_per_second": 2.95,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.590380257784627e+16,
+  "total_flos": 9.877352954934067e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null