Training in progress, epoch 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "down_proj",
-    "q_proj",
-    "k_proj",
+    "o_proj",
     "gate_proj",
+    "k_proj",
     "up_proj",
+    "q_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1ac2cde4d6de38916287a0f92576746b8b912405a05e9927d9b7c43e6ad2b80
+oid sha256:e979dbd3cbd940f959a4ba68cfe39ed192ba6aaf26b940558b355981237dddf9
 size 69527352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9c0e178c57991d9b6c6637d99eafc6561e3fa4f68fde4e5eb906cb2276572dc
+oid sha256:39a2e574caffeb2fdfdb41ce93130d1ac0d397bbcadbeb7dd4e2d64b60937f1b
 size 35778900

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:679d9461f52487b2177f87f4dca8924af37af2c10803eb70744c2e4f376d3c2d
+oid sha256:5aff15d3484f18cecf83b769183ac0cc241615e7ba3d43c9e65497b2930f18c5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:884dbcf1f76cdf64d0ca16f2c81847fd9a35ed97a8bdfbbdeee456fb385a47c3
+oid sha256:bcf348532606e290f3cddebc7f00005cce6f05bb1cced2bad1d4a15482755657
 size 1064

last-checkpoint/trainer_state.json

@@ -1,112 +1,69 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6348773841961854,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 600,
+  "global_step": 367,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.1362397820163488,
-      "grad_norm": 0.7698700428009033,
+      "grad_norm": 0.784312903881073,
       "learning_rate": 0.0004,
-      "loss": 1.3953,
+      "loss": 1.3927,
       "step": 50
     },
     {
       "epoch": 0.2724795640326976,
-      "grad_norm": 0.5740014910697937,
+      "grad_norm": 0.5759815573692322,
       "learning_rate": 0.0004,
-      "loss": 0.8509,
+      "loss": 0.8469,
       "step": 100
     },
     {
       "epoch": 0.4087193460490463,
-      "grad_norm": 0.7224377989768982,
+      "grad_norm": 0.7147420048713684,
       "learning_rate": 0.0004,
-      "loss": 0.6471,
+      "loss": 0.6428,
       "step": 150
     },
     {
       "epoch": 0.5449591280653951,
-      "grad_norm": 1.064605474472046,
+      "grad_norm": 1.0268043279647827,
       "learning_rate": 0.0004,
-      "loss": 0.5458,
+      "loss": 0.5406,
       "step": 200
     },
     {
       "epoch": 0.6811989100817438,
-      "grad_norm": 0.5921716690063477,
+      "grad_norm": 0.5647836923599243,
       "learning_rate": 0.0004,
-      "loss": 0.4329,
+      "loss": 0.4279,
       "step": 250
     },
     {
       "epoch": 0.8174386920980926,
-      "grad_norm": 0.403538316488266,
+      "grad_norm": 0.48977088928222656,
       "learning_rate": 0.0004,
-      "loss": 0.3786,
+      "loss": 0.3726,
       "step": 300
     },
     {
       "epoch": 0.9536784741144414,
-      "grad_norm": 0.4223729372024536,
+      "grad_norm": 0.3192068636417389,
       "learning_rate": 0.0004,
-      "loss": 0.3036,
+      "loss": 0.3033,
       "step": 350
     },
     {
       "epoch": 1.0,
-      "eval_loss": 0.25390318036079407,
-      "eval_runtime": 4.2748,
-      "eval_samples_per_second": 72.284,
-      "eval_steps_per_second": 18.247,
+      "eval_loss": 0.2556329667568207,
+      "eval_runtime": 4.2889,
+      "eval_samples_per_second": 72.046,
+      "eval_steps_per_second": 18.186,
       "step": 367
-    },
-    {
-      "epoch": 1.0899182561307903,
-      "grad_norm": 0.2040538489818573,
-      "learning_rate": 0.0004,
-      "loss": 0.2737,
-      "step": 400
-    },
-    {
-      "epoch": 1.226158038147139,
-      "grad_norm": 0.2643136978149414,
-      "learning_rate": 0.0004,
-      "loss": 0.1975,
-      "step": 450
-    },
-    {
-      "epoch": 1.3623978201634879,
-      "grad_norm": 0.3208156228065491,
-      "learning_rate": 0.0004,
-      "loss": 0.1744,
-      "step": 500
-    },
-    {
-      "epoch": 1.4986376021798364,
-      "grad_norm": 0.314196914434433,
-      "learning_rate": 0.0004,
-      "loss": 0.1536,
-      "step": 550
-    },
-    {
-      "epoch": 1.6348773841961854,
-      "grad_norm": 0.44153332710266113,
-      "learning_rate": 0.0004,
-      "loss": 0.1304,
-      "step": 600
-    },
-    {
-      "epoch": 1.6348773841961854,
-      "eval_loss": 0.1265459954738617,
-      "eval_runtime": 4.2648,
-      "eval_samples_per_second": 72.453,
-      "eval_steps_per_second": 18.289,
-      "step": 600
     }
   ],
   "logging_steps": 50,
@@ -121,12 +78,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.945276023865344e+16,
+  "total_flos": 1.189318078660608e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbdf780f678ce24abeccef8a93bd5140aadf5e01c25177d8fa09c1018ecfa471
+oid sha256:2a656ef5d64b69ea7ac8f230e33aea3f20620e500bf2a829f86b58a5ee64c52b
 size 6776