Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:456101da57817a6c6eab70ca3c9f99d35dbde579121bd9acc21deae728f4b753
+oid sha256:746cb2a18d6d1f561bc3aff47b7aa22e3c682e3f2e4f762807089d6a6449cee2
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2728aa34cb99a7118d9bc3f76f97cb9f975d7936fe5549ea29e90f0509d56b7
+oid sha256:783ace743b00db24851b4595cdf81cd62cd4c55c82088a2f436820a3d57cd7ef
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c9035a1288e95b2d7bec3113aa299aec1bffd2c4de16b0eb57152073d87288
+oid sha256:047bd246ac1b276cbb1c42a59b852f224774db2a5ba632646833eafba7e996a8
 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": 0.09385265133740028,
+  "epoch": 0.18770530267480057,
   "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": 9.706,
       "eval_steps_per_second": 4.874,
       "step": 25
+    },
+    {
+      "epoch": 0.09760675739089629,
+      "grad_norm": 1.7941869497299194,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.1451,
+      "step": 26
+    },
+    {
+      "epoch": 0.10136086344439231,
+      "grad_norm": 4.530095100402832,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.2568,
+      "step": 27
+    },
+    {
+      "epoch": 0.10511496949788832,
+      "grad_norm": 2.566866636276245,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.1024,
+      "step": 28
+    },
+    {
+      "epoch": 0.10886907555138432,
+      "grad_norm": 1.405090570449829,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.0991,
+      "step": 29
+    },
+    {
+      "epoch": 0.11262318160488034,
+      "grad_norm": 1.2196756601333618,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0372,
+      "step": 30
+    },
+    {
+      "epoch": 0.11637728765837635,
+      "grad_norm": 2.8575334548950195,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.1209,
+      "step": 31
+    },
+    {
+      "epoch": 0.12013139371187236,
+      "grad_norm": 1.67503821849823,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.0985,
+      "step": 32
+    },
+    {
+      "epoch": 0.12388549976536838,
+      "grad_norm": 2.7599682807922363,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.1226,
+      "step": 33
+    },
+    {
+      "epoch": 0.12763960581886438,
+      "grad_norm": 0.700145423412323,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.0623,
+      "step": 34
+    },
+    {
+      "epoch": 0.1313937118723604,
+      "grad_norm": 1.034289836883545,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0414,
+      "step": 35
+    },
+    {
+      "epoch": 0.1351478179258564,
+      "grad_norm": 2.3948283195495605,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.0645,
+      "step": 36
+    },
+    {
+      "epoch": 0.13890192397935242,
+      "grad_norm": 4.111328125,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.1108,
+      "step": 37
+    },
+    {
+      "epoch": 0.14265603003284844,
+      "grad_norm": 2.2279419898986816,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.0874,
+      "step": 38
+    },
+    {
+      "epoch": 0.14641013608634443,
+      "grad_norm": 1.1830275058746338,
+      "learning_rate": 5e-05,
+      "loss": 0.0498,
+      "step": 39
+    },
+    {
+      "epoch": 0.15016424213984045,
+      "grad_norm": 0.3365573585033417,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.0223,
+      "step": 40
+    },
+    {
+      "epoch": 0.15391834819333647,
+      "grad_norm": 2.0155816078186035,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.1617,
+      "step": 41
+    },
+    {
+      "epoch": 0.15767245424683246,
+      "grad_norm": 3.003706455230713,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.102,
+      "step": 42
+    },
+    {
+      "epoch": 0.16142656030032848,
+      "grad_norm": 1.5898525714874268,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0484,
+      "step": 43
+    },
+    {
+      "epoch": 0.1651806663538245,
+      "grad_norm": 0.8386490345001221,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.0363,
+      "step": 44
+    },
+    {
+      "epoch": 0.1689347724073205,
+      "grad_norm": 1.006565809249878,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0238,
+      "step": 45
+    },
+    {
+      "epoch": 0.17268887846081651,
+      "grad_norm": 1.485731601715088,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.0654,
+      "step": 46
+    },
+    {
+      "epoch": 0.17644298451431253,
+      "grad_norm": 1.6186491250991821,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.1113,
+      "step": 47
+    },
+    {
+      "epoch": 0.18019709056780855,
+      "grad_norm": 2.721684217453003,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.1347,
+      "step": 48
+    },
+    {
+      "epoch": 0.18395119662130455,
+      "grad_norm": 0.671211302280426,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.0177,
+      "step": 49
+    },
+    {
+      "epoch": 0.18770530267480057,
+      "grad_norm": 0.7374471426010132,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.0291,
+      "step": 50
+    },
+    {
+      "epoch": 0.18770530267480057,
+      "eval_loss": 0.03728002309799194,
+      "eval_runtime": 23.2151,
+      "eval_samples_per_second": 9.692,
+      "eval_steps_per_second": 4.868,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.49519346663424e+16,
+  "total_flos": 6.99038693326848e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null